feat(api): Add image multimodal support for LLMNode (#17372)

Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.

This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.

To integrate file outputs into workflows, adjustments to the frontend code
are necessary.

For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.

Close #15814.

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>

api/models/model.py

@@ -8,6 +8,7 @@ from typing import TYPE_CHECKING, Any, Literal, Optional, cast
 
 from core.plugin.entities.plugin import GenericProviderID
 from core.tools.entities.tool_entities import ToolProviderType
+from core.tools.signature import sign_tool_file
 from services.plugin.plugin_service import PluginService
 
 if TYPE_CHECKING:
@@ -23,7 +24,6 @@ from configs import dify_config
 from constants import DEFAULT_FILE_NUMBER_LIMITS
 from core.file import FILE_MODEL_IDENTITY, File, FileTransferMethod, FileType
 from core.file import helpers as file_helpers
-from core.file.tool_file_parser import ToolFileParser
 from libs.helper import generate_string
 from models.base import Base
 from models.enums import CreatedByRole
@@ -986,9 +986,7 @@ class Message(db.Model):  # type: ignore[name-defined]
                 if not tool_file_id:
                     continue
 
-                sign_url = ToolFileParser.get_tool_file_manager().sign_file(
-                    tool_file_id=tool_file_id, extension=extension
-                )
+                sign_url = sign_tool_file(tool_file_id=tool_file_id, extension=extension)
             elif "file-preview" in url:
                 # get upload file id
                 upload_file_id_pattern = r"\/files\/([\w-]+)\/file-preview?\?timestamp="